Sentiment Analysis of Public Perceptions of the President’s Policy on the National Disaster Status in Sumatra Using a Social Media-Based Naive Bayes Model X
Analisis Sentimen Persepsi Publik terhadap Kebijakan Presiden tentang Status Bencana Nasional di Sumatera Dengan Naive Bayes Berbasis Media Sosial X
DOI:
https://doi.org/10.21070/ups.11488Keywords:
Sentiment Analysis, Naïve Bayes, TF-IDF, National Disaster, X Social MediaAbstract
The widespread use of the X platform makes it a primary channel for public responses to government policies. This study examines public sentiment regarding the President's national disaster status for the Sumatra floods by comparing three Naïve Bayes algorithms: Multinomial, Bernoulli, and Complement. Scraping yielded 1,208 tweets, which underwent preprocessing, TF-IDF extraction, and oversampling on an 80:20 training split to resolve extreme label imbalance, expanding the training dataset to 2,685. Results showed that while Multinomial and Bernoulli achieved over 92% accuracy, both suffered from an accuracy paradox and severe overfitting, failing to detect minority classes. Conversely, Complement Naïve Bayes proved highly robust, achieving 87.60% accuracy and the highest Macro F1-Score (0.49) to successfully capture minority sentiments. Topic analysis revealed that negative sentiments criticized the Ministry of Public Works over damaged infrastructure, whereas positive sentiments appreciated rapid relief efforts. This research offers insights for evaluating disaster communications.
References
S. Jurnal, “( S I N T E K ) ANALISIS SENTIMEN BENCANA BANJIR SUMATERA MENGGUNAKAN TF-IDF DAN LOGISTIC REGRESSION,” vol. VI, no. 1.
F. Meila, A. Sofyan, N. Sulistiyowati, and A. Voutama, “ANALISIS SENTIMEN TERHADAP RESPON PERUBAHAN NAMA TWITTER MENJADI ‘ X ’ MENGGUNAKAN METODE NAÏVE BAYES CLASSIFIER,” vol. 8, no. 5, pp. 10987–10994, 2024.
I. Iskandar, “Model Komunikasi Kebencanaan Berbasis Analisis Sentimen dan Jaringan Sosial di Twitter dan Instagram Untuk Mitigasi Banjir di Kota Makassar,” vol. 5, no. 1, pp. 202–222, 2026.
Z. Zulkarnaini, H. Purnomo, and A. Firdhayanti, “Klasifikasi Sentimen Ulasan Pengguna MyPertamina Menggunakan Algoritma Naive Bayes dan TF-IDF: Klasifikasi Sentimen Ulasan Pengguna MyPertamina Menggunakan Algoritma Naive Bayes dan TF-IDF,” JUPITER J. Penelit. Ilmu dan Teknol. Komput., vol. 17, no. 2, pp. 801–810, 2025, [Online]. Available: https://jurnal.polsri.ac.id/index.php/jupiter/article/view/10600
T. Menggunakan, M. T. Dan, and N. Bayes, “Jurnal Informatika Terpadu TWITTER MENGGUNAKAN METODE TF-IDF DAN NAIVE BAYES,” vol. 10, no. 2, pp. 93–100, 2024.
Y. Pramana, Y. Pradeva, I. M. Widiartha, and I. P. Satwika, “Analisis Sentimen Kebijakan Insentif Mobil Listrik Menggunakan TF-IDF dan Naïve Bayes,” vol. 4, no. November, pp. 181–188, 2025.
S. Khoerunnisa, D. F. Shiddieq, and D. Nurhayati, “Penerapan Algoritma Naive Bayes dengan Teknik TF-IDF dan Cross Validation untuk Analisis Sentimen Terhadap Starlink,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 2, pp. 566–577, 2025, doi: 10.57152/malcom.v5i2.1852.
Ardiansyah, Adika Sri Widagdo, Krisna Nuresa Qodri, F. E. N. Saputro, and Nisrina Akbar Rizky P, “Analisis sentimen terhadap pelayanan Kesehatan berdasarkan ulasan Google Maps menggunakan BERT,” J. Fasilkom, vol. 13, no. 02, pp. 326–333, 2023, doi: 10.37859/jf.v13i02.5170.
D. F. Zhafira, B. Rahayudi, and Indriati, “Analisis Sentimen Kebijakan Kampus Merdeka Menggunakan Naïve Bayes dan Pembobotan TF-IDF,” J. Sist. Informasi, Teknol. Informasi, dan Edukasi Sist. Inf., vol. 2, no. 1, pp. 55–63, 2021.
Sulton Ibrahim, Widodo, and Murien Nugraheni, “Analisis Sentimen Pengguna Twitter Terhadap Kebijakan Pemerintah Dalam Menangani Covid-19 Menggunakan Metode Support Vector Machine Dan Naive Bayes Dengan Laplace Estimator,” PINTER J. Pendidik. Tek. Inform. dan Komput., vol. 9, no. 1, pp. 47–54, 2025, doi: 10.21009/pinter.9.1.7.
Y. Hapsari, S. Mujahidin, and N. Fadhliana, “Analisis Sentimen Isu Vaksinasi Covid-19 pada Twitter dengan Metode Naive Bayes dan Pembobotan TF-IDF Tokenisasi 1-2 Gram,” SPECTA J. Technol., vol. 7, no. 2, pp. 573–583, 2023, doi: 10.35718/specta.v7i2.812.
P. Indobert, “Sentiment Analysis of Coretax : A Comparison of Manual , Transformers- Based , and Lexicon-Based Data Labeling on IndoBERT Performance Analisis Sentimen Coretax : Perbandingan Pelabelan Data Manual ,” vol. 5, no. July, pp. 1037–1048, 2025.
M. S. Assyifa et al., “Sentiment Analysis of STMIK Widya Cipta Dharma Using a Lexicon-Based Approach Analisis Sentimen Terhadap STMIK Widya Cipta Dharma Menggunakan Pendekatan Lexicon,” pp. 1–7.
A. N. Halim, R. Rudiman, and N. A. Verdikha, “Analisis Sentimen Opini Publik Terhadap Peristiwa Bitcoin Halving Pada Data Teks Twitter Menggunakan Metode Naïve Bayes Dan Pembobotan Fitur TF-IDF,” RIGGS J. Artif. Intell. Digit. Bus., vol. 4, no. 3, pp. 2823–2831, 2025, doi: 10.31004/riggs.v4i3.2291.
I. Arief, S. Defit, and G. Widi, “Development of Extraction Features for Detecting Adolescent Personality with Machine Learning Algorithms,” vol. 8, no. November, 2024.
M. N. Dewi and R. E. Putra, “Pengembangan Sistem Analisis Sentimen Masyarakat Terhadap Chatgpt Pada Twitter Dengan Perbandingan Metode Naive Bayes Classifier Dan K-Nearest Neighbors,” pp. 344–357.
H. L. Panggabean, F. Gultom, M. Bobbi, K. Nasution, * Helmud, and L. Panggabean, “Analisis Sentimen terhadap Rumah Sakit Tarutung Berdasarkan Google Maps Review Menggunakan Algoritma Naïve Bayes dan Pembobotan Kata Tf-Idf,” J. Pendidik. Sains dan Komput., vol. 5, no. 02, pp. 2809–476, 2025, [Online]. Available: https://doi.org/10.47709/jpsk.v5i02.7352
N. Annisa Murnastiti and T. Noor Fatyanosa, “Analisis Sentimen Terhadap Makanan Manis di Platform X Menggunakan TF-IDF dan Naive Bayes,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 1, pp. 2548–964, 2025, [Online]. Available: http://j-ptiik.ub.ac.id
L. A. Qomariah et al., “KLASIFIKASI SENTIMEN ULASAN MINECRAFT PADA GOOGLE PLAY STORE : STUDI KOMPARATIF NAÏVE BAYES DAN RANDOM FOREST,” vol. 10, no. 1, pp. 1227–1234, 2026.
P. Keterampilan and M. Berbasis, “RISET : Jurnal Ilmiah Multidisiplin Ilmu,” vol. 1, no. 1, 2025.
D. I. Mulyana and A. S. Sumarsono, “Jurnal Indonesia : Manajemen Informatika dan Komunikasi PENERAPAN METODE NEURAL NETWORK DENGAN Abstrak Jurnal Indonesia : Manajemen Informatika dan Komunikasi,” vol. 4, no. 1, pp. 121–128, 2023.
M. M. Arif and H. Setiawan, “The Use Of Data Mining To Predict Student Study Period At Muhammadiyah University Sidoarjo By Using Naive Bayes Algorithm [ Penggunaan Datamining Untuk Memprediksi Masa Studi Mahasiswa di Universitas Muhammadiyah Sidoarjo Dengan Algoritma Naive Bayes ],” pp. 1–6, 2020.
Downloads
Additional Files
Posted
Categories
License
Copyright (c) 2026 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
